INDEX

Explanations

the prefix "mon" in various words, though some signal words appear related to installs, and macrophage activity signaling

oai_token-act-pair · gemini-2.0-flash

mon

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Chham

-0.84

 дописавши

-0.79

IsContent

-0.72

AddTagHelper

-0.71

AnchorStyles

-0.69

awaiter

-0.69

DockStyle

-0.68

<?

-0.66

 ostavi

-0.66

SequentialGroup

-0.66

POSITIVE LOGITS

Gizmos

0.44

ButtonModule

0.43

роль

0.42

 גע

0.42

 civiles

0.42

Serializable

0.40

 klink

0.40

 traded

0.40

ハウ

0.39

 balne

0.38

Activations Density 7.685%

the prefix "mon" in various words, though some signal words appear related to installs, and macrophage activity signaling

mon

No Comments

No Known Activations